Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{204053,
        author = {Aman Kumar and Chiman Saini and Sangeeta Rani},
        title = {Autonomous Decision Intelligence with Generative Agentic AI for Climate Forecasting and Disaster Early Warning: A Comprehensive Review},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {614-620},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204053},
        abstract = {Climate instability and the growing intensity of environmental disasters have increased the need for intelligent forecasting and rapid disaster response systems. Conventional climate forecasting models often struggle to process dynamic environmental conditions, large-scale real-time datasets, and rapidly evolving disaster situations. Recent developments in Artificial Intelligence (AI), particularly Generative AI and Agentic AI, have introduced a new paradigm for autonomous climate intelligence and disaster management. This review paper presents a detailed analysis of intelligent Agentic AI systems designed for climate prediction and disaster early warning applications. The study critically reviews the proposed Generative Agentic AI framework that combines deep learning architectures, autonomous decision-making agents, reinforcement learning, and adaptive reasoning mechanisms to improve forecasting performance and emergency response efficiency.
The review synthesizes findings from recent research related to GeoAI, digital twins, open-world machine learning, large language model agents, climate simulation systems, and intelligent environmental analytics. The paper discusses the evolution from traditional machine learning systems toward fully autonomous environmental intelligence frameworks capable of adaptive learning, contextual reasoning, and real-time coordination. The proposed framework demonstrates significant improvements in forecasting accuracy, disaster warning lead time, response prioritization, and operational scalability compared to conventional climate prediction systems.
This review further explores the major technical, ethical, and operational challenges associated with Agentic AI systems, including data dependency, interpretability, cybersecurity, governance, computational complexity, and scalability. The paper concludes that Agentic AI represents a transformative direction for next-generation climate forecasting and disaster management systems capable of supporting sustainable environmental resilience and intelligent emergency response ecosystems.},
        keywords = {Agentic AI, Generative Artificial Intelligence, Climate Prediction, Disaster Early Warning, Environmental Intelligence, Autonomous Decision Systems, Deep Learning, Multi-Agent Systems, Climate Resilience.},
        month = {June},
        }